Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
Abstract
We introduce a new generation of small reasoning models for RAG, search, and source summarization. Pleias-RAG-350m and Pleias-RAG-1B are mid-trained on a large synthetic dataset emulating the retrieval of a wide variety of multilingual open sources from the Common Corpus. They provide native support for citation and grounding with literal quotes and reintegrate multiple features associated with RAG workflows, such as query routing, query reformulation, and source reranking. Pleias-RAG-350m and Pleias-RAG-1B outperform SLMs below 4 billion parameters on standardized RAG benchmarks (HotPotQA, 2wiki) and are competitive with popular larger models, including Qwen-2.5-7B, Llama-3.1-8B, and Gemma-3-4B. They are the only SLMs to date maintaining consistent RAG performance across leading European languages and ensuring systematic reference grounding for statements. Due to their size and ease of deployment on constrained infrastructure and higher factuality by design, the models unlock a range of new use cases for generative AI.
Community
Detailed model paper describing the mid-training recipe of Pleias-350M (https://huggingface.co/PleIAs/Pleias-RAG-350M) and Pleias-1B (https://huggingface.co/PleIAs/Pleias-RAG-1B).
Currently SOTA model in their size range for RAG.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration (2025)
- XL-Instruct: Synthetic Data for Cross-Lingual Open-Ended Generation (2025)
- Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks (2025)
- FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation (2025)
- Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning (2025)
- MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation (2025)
- MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper